Research map / Image generation / Image restoration
Deep Restoration of Vintage Photographs From Scanned Halftone Prints
Qifan Gao, Xiao Shu, Xiaolin Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the artifacts removal subnet (ablation) | two-stage halftone restoration · real vintage halftone prints | visual quality | Improved |
| add the inverse halftoning subnet (ablation) | two-stage halftone restoration · real vintage halftone prints | visual quality | Improved |
| add joint fine-tuning of both subnets (ablation) | two-stage halftone restoration · real vintage halftone prints | visual quality | Improved |
| pre-process input with the artifacts removal subnet Ns | Unet · real vintage halftone prints | visual quality | Improved |
| use the proposed two-stage method instead of ESRGAN on synthetic data | two-stage halftone restoration · synthetic halftone test set | PSNR: 29.94 -> 30.10 | Improved |
| use the proposed method instead of Unet on synthetic data | two-stage halftone restoration · synthetic halftone test set | PSNR: 28.60 -> 30.10 | Improved |
| use the proposed method instead of Sattva as MTCNN input | two-stage halftone restoration · real vintage halftone prints | face detection accuracy: 0.7484 -> 0.7576 | Improved |
| restore with the proposed method instead of raw halftone input | two-stage halftone restoration · real vintage halftone prints | face detection accuracy: 0.6012 -> 0.7576 | Improved |
| use the proposed method instead of ESRGAN in model cost | two-stage halftone restoration · 512x512 image | computation time (s): 0.054 -> 0.042 | Hurt |
Closest papers by meaning
- Conditional Diffusion Process for Inverse Halftoning (NeurIPS 2022 · similarity 0.87)
- Descanning: From Scanned to the Original Images with a Color Correction Diffusion Model (AAAI 2024 · similarity 0.85)
- ReFIR: Grounding Large Restoration Models with Retrieval Augmentation (NeurIPS 2024 · similarity 0.84)
- Predicting the Original Appearance of Damaged Historical Documents (AAAI 2025 · similarity 0.83)
- Ink Dot-Oriented Differentiable Optimization for Neural Image Halftoning (CVPR 2024 · similarity 0.83)
- Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
